Dissertation > Excellent graduate degree dissertation topics show

Extended SDM model and its application in prediction and recognition

Author: SunBingTong
Tutor: ChenSongCan
School: Nanjing University of Aeronautics and Astronautics
Course: Computer Software and Theory
Keywords: Neural network SDM LMSE (G)SOFM Time-series Prediction Character recognition
CLC: TP183
Type: Master's thesis
Year: 2002
Downloads: 34
Quote: 0
Read: Download Dissertation

Abstract


Kanerva’s Sparse Distributed Memory (SDM) can realize the problem of training and recognizing patterns with large dimension due to its sparse address choice and data storage in the distributed mode. It simulates the partial function of human cerebellum to a certain extent, generalizes random access mode of current computers and is applied in many domains such as pattern recognition and associative memories. Because of randomness of presetting the address matrix between the input and hidden layers, SDM produces unfavorable consequences for classification when handling unevenly distributed patterns. And its learning mode of outer product results in poor nonlinear mapping ability. In this dissertation, we present an extended SDM which can overcome the original SDM poor nonlinear mapping ability by modifying original presetting mode of address matrix and learning algorithm on the basic of former studies.In the ExSDM, binary coding for input data is replaced by direct real-valued inputs, accordingly, avoiding the coding process for data like in SDM. The outer learning rule is replaced by Least Means Squares Error(LMSE), therefore the model has not only the ability of pattern recognition but also the ability of function approximation. The prestting mode of address matrix is automatically decided by sample distribution with the help of (grey) self-organizing feature map ((G)SOFM) so as to reflect the actual sample distribution. The transfer function of the hidden layer is Gaussian function. The computer simulations for non-linear function approximation, time-series prediction and handwritten numeral recognition show that the modified model is effective and feasible.

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  3. Municipal tourism land use planning environmental impact assessment,X820.3
  4. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  5. BP network optimization based on genetic algorithm optimization of the biodiesel process,TE667
  6. Research on Inspection Technology of Dehydrated Garlic Slice Based on Computer Vision,TP391.41
  7. The Design of the Coal Mine’s Safety Evaluation System Based on Wavelet Neural Network,TD79
  8. Application of Fuzzy Neural Network in mine plow system,TJ518
  9. Study on a New Method for Digital Transformer Protection Based on Wavelet Neural Network and FPGA,TM407
  10. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  11. Automatic Recognition analyze of Fabric Structure Based on GLCM and BP Neural Network,TP391.41
  12. Based on Data Mining Technologies in Urban Water Supply Analysis and Decision,F299.24;F224
  13. Research on NO-reference Image Quality Assessment Based on HVS,TP391.41
  14. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  15. A Research on Prediction of Academic Record Based on Neural Network and Cover Algorithm,TP311.13
  16. Object-Oriented Analysis Based on Neutral Network,TP311.52
  17. The Application Research of City Meteorological Forecast Based on Genetic Neural Network,P45
  18. Application Research of Genetic Neural Network in Surface Water Evaluation,X824
  19. Reliability Robust Design of Impeller of Large Centrifugal Compressor,TH452
  20. Based on Lifting Scheme Wavelet Packet Transform and Artificial Neural Network Wing-box Multi-damage Detection,V224
  21. Research of Safety Stock Prediction Model Based on Improved BP Algorithm,O227

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile